Researcher Profile

Dr. Prakash Poudyal

Information

Assistant Professor

Kathmandu University

prakash@ku.edu.np

External Profile

Research Domain
  • Information Retrieval
  • Low-Resource Languages
  • Speech Processing
  • Machine Translation

Bio

Publications

Improving Accuracy of Low-resource ASR using Rule-Based Character Constituency Loss (RBCCL)

Mr. Rupak Raj Ghimire | Dr. Prakash Poudyal | Prof.Dr. Bal Krishna Bal 

Rupak Raj Ghimire, Prakash Poudyal, and Bal Krishna Bal. 2025. Improving Accuracy of Low-resource ASR using Rule-Based Character Constituency Loss (RBCCL). In Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025), pages 61–70, Abu Dhabi, UAE. International Committee on Computational Linguistics.

Improving on the Limitations of the ASR Model in Low-Resourced Environments Using Parameter-Efficient Fine-Tuning

Mr. Rupak Raj Ghimire | Dr. Prakash Poudyal | Prof.Dr. Bal Krishna Bal 

Rupak Raj Ghimire, Prakash Poudyal, and Bal Krishna Bal. 2024. Improving on the Limitations of the ASR Model in Low-Resourced Environments Using Parameter-Efficient Fine-Tuning. In Proceedings of the 21st International Conference on Natural Language Processing (ICON), pages 408–415, AU-KBC Research Centre, Chennai, India. NLP Association of India (NLPAI).

A Comprehensive Study of the Current State-of-the-Art in Nepali Automatic Speech Recognition Systems

Mr. Rupak Raj Ghimire | Prof.Dr. Bal Krishna Bal | Dr. Prakash Poudyal 

Rupak Raj Ghimire, Bal Krishna Bal, Prakash Poudyal (2023). A Comprehensive Study of the Current State-of-the-Art in Nepali Automatic Speech Recognition Systems. International Conference on Technologies for Computer, Electrical, Electronics & Communication (ICT-CEEL 2023), 11’th - 13’th October 2023, Bhaktapur, Nepal.

Active Learning Approach for Fine-Tuning Pre-Trained ASR Model for a Low-Resourced Language: A Case Study of Nepali

Mr. Rupak Raj Ghimire | Prof.Dr. Bal Krishna Bal | Dr. Prakash Poudyal 

Rupak Raj Ghimire, Bal Krishna Bal, and Prakash Poudyal. 2023. Active Learning Approach for Fine-Tuning Pre-Trained ASR Model for a Low-Resourced Language: A Case Study of Nepali. In Proceedings of the 20th International Conference on Natural Language Processing (ICON), pages 82–89, Goa University, Goa, India. NLP Association of India (NLPAI).

Pronunciation-Aware Syllable Tokenizer for Nepali Automatic Speech Recognition System

Mr. Rupak Raj Ghimire | Prof.Dr. Bal Krishna Bal | Prof.Dr. Balaram Prasain | Dr. Prakash Poudyal 

Rupak Raj Ghimire, Bal Krishna Bal, Balaram Prasain, Prakash Poudyal (2023). Pronunciation-Aware Syllable Tokenizer for Nepali Automatic Speech Recognition System. In Proceedings of the 20th International Conference on Natural Language Processing (ICON), pages 36–43, Goa University, Goa, India. NLP Association of India (NLPAI).